Extracting and Visualizing Stock Data
Description
Extracting essential data from a dataset and displaying it is a necessary part of data science; therefore individuals can make correct decisions based on the data. In this assignment, you will extract some stock data, you will then display this data in a graph.
Table of Contents
- Define a Function that Makes a Graph
- Question 1: Use yfinance to Extract Stock Data
- Question 2: Use Webscraping to Extract Tesla Revenue Data
- Question 3: Use yfinance to Extract Stock Data
- Question 4: Use Webscraping to Extract GME Revenue Data
- Question 5: Plot Tesla Stock Graph
- Question 6: Plot GameStop Stock Graph
Estimated Time Needed: 30 min
Note:- If you are working Locally using anaconda, please uncomment the following code and execute it. Use the version as per your python version.
!pip install yfinance
!pip install bs4
!pip install nbformat
Collecting yfinance
Downloading yfinance-0.2.52-py2.py3-none-any.whl.metadata (5.8 kB)
Collecting pandas>=1.3.0 (from yfinance)
Downloading pandas-2.2.3-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl.metadata (89 kB)
Collecting numpy>=1.16.5 (from yfinance)
Downloading numpy-2.2.3-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl.metadata (62 kB)
Requirement already satisfied: requests>=2.31 in /opt/conda/lib/python3.12/site-packages (from yfinance) (2.32.3)
Collecting multitasking>=0.0.7 (from yfinance)
Downloading multitasking-0.0.11-py3-none-any.whl.metadata (5.5 kB)
Collecting lxml>=4.9.1 (from yfinance)
Downloading lxml-5.3.1-cp312-cp312-manylinux_2_28_x86_64.whl.metadata (3.7 kB)
Requirement already satisfied: platformdirs>=2.0.0 in /opt/conda/lib/python3.12/site-packages (from yfinance) (4.3.6)
Requirement already satisfied: pytz>=2022.5 in /opt/conda/lib/python3.12/site-packages (from yfinance) (2024.2)
Requirement already satisfied: frozendict>=2.3.4 in /opt/conda/lib/python3.12/site-packages (from yfinance) (2.4.6)
Collecting peewee>=3.16.2 (from yfinance)
Downloading peewee-3.17.9.tar.gz (3.0 MB)
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 3.0/3.0 MB 61.9 MB/s eta 0:00:00
Installing build dependencies ... one
Getting requirements to build wheel ... done
Preparing metadata (pyproject.toml) ... done
Requirement already satisfied: beautifulsoup4>=4.11.1 in /opt/conda/lib/python3.12/site-packages (from yfinance) (4.12.3)
Collecting html5lib>=1.1 (from yfinance)
Downloading html5lib-1.1-py2.py3-none-any.whl.metadata (16 kB)
Requirement already satisfied: soupsieve>1.2 in /opt/conda/lib/python3.12/site-packages (from beautifulsoup4>=4.11.1->yfinance) (2.5)
Requirement already satisfied: six>=1.9 in /opt/conda/lib/python3.12/site-packages (from html5lib>=1.1->yfinance) (1.17.0)
Requirement already satisfied: webencodings in /opt/conda/lib/python3.12/site-packages (from html5lib>=1.1->yfinance) (0.5.1)
Requirement already satisfied: python-dateutil>=2.8.2 in /opt/conda/lib/python3.12/site-packages (from pandas>=1.3.0->yfinance) (2.9.0.post0)
Collecting tzdata>=2022.7 (from pandas>=1.3.0->yfinance)
Downloading tzdata-2025.1-py2.py3-none-any.whl.metadata (1.4 kB)
Requirement already satisfied: charset_normalizer<4,>=2 in /opt/conda/lib/python3.12/site-packages (from requests>=2.31->yfinance) (3.4.1)
Requirement already satisfied: idna<4,>=2.5 in /opt/conda/lib/python3.12/site-packages (from requests>=2.31->yfinance) (3.10)
Requirement already satisfied: urllib3<3,>=1.21.1 in /opt/conda/lib/python3.12/site-packages (from requests>=2.31->yfinance) (2.3.0)
Requirement already satisfied: certifi>=2017.4.17 in /opt/conda/lib/python3.12/site-packages (from requests>=2.31->yfinance) (2024.12.14)
Downloading yfinance-0.2.52-py2.py3-none-any.whl (108 kB)
Downloading html5lib-1.1-py2.py3-none-any.whl (112 kB)
Downloading lxml-5.3.1-cp312-cp312-manylinux_2_28_x86_64.whl (5.0 MB)
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 5.0/5.0 MB 90.8 MB/s eta 0:00:00
Downloading multitasking-0.0.11-py3-none-any.whl (8.5 kB)
Downloading numpy-2.2.3-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (16.1 MB)
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 16.1/16.1 MB 195.4 MB/s eta 0:00:00
Downloading pandas-2.2.3-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (12.7 MB)
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 12.7/12.7 MB 189.3 MB/s eta 0:00:00
Downloading tzdata-2025.1-py2.py3-none-any.whl (346 kB)
Building wheels for collected packages: peewee
Building wheel for peewee (pyproject.toml) ... one
Created wheel for peewee: filename=peewee-3.17.9-cp312-cp312-linux_x86_64.whl size=303803 sha256=1b4cc0188861d6cf4a9f618650a9aa24f120dc70aecb999f43faa45a2edbbb18
Stored in directory: /home/jupyterlab/.cache/pip/wheels/43/ef/2d/2c51d496bf084945ffdf838b4cc8767b8ba1cc20eb41588831
Successfully built peewee
Installing collected packages: peewee, multitasking, tzdata, numpy, lxml, html5lib, pandas, yfinance
Successfully installed html5lib-1.1 lxml-5.3.1 multitasking-0.0.11 numpy-2.2.3 pandas-2.2.3 peewee-3.17.9 tzdata-2025.1 yfinance-0.2.52
Collecting bs4
Downloading bs4-0.0.2-py2.py3-none-any.whl.metadata (411 bytes)
Requirement already satisfied: beautifulsoup4 in /opt/conda/lib/python3.12/site-packages (from bs4) (4.12.3)
Requirement already satisfied: soupsieve>1.2 in /opt/conda/lib/python3.12/site-packages (from beautifulsoup4->bs4) (2.5)
Downloading bs4-0.0.2-py2.py3-none-any.whl (1.2 kB)
Installing collected packages: bs4
Successfully installed bs4-0.0.2
Requirement already satisfied: nbformat in /opt/conda/lib/python3.12/site-packages (5.10.4)
Requirement already satisfied: fastjsonschema>=2.15 in /opt/conda/lib/python3.12/site-packages (from nbformat) (2.21.1)
Requirement already satisfied: jsonschema>=2.6 in /opt/conda/lib/python3.12/site-packages (from nbformat) (4.23.0)
Requirement already satisfied: jupyter-core!=5.0.*,>=4.12 in /opt/conda/lib/python3.12/site-packages (from nbformat) (5.7.2)
Requirement already satisfied: traitlets>=5.1 in /opt/conda/lib/python3.12/site-packages (from nbformat) (5.14.3)
Requirement already satisfied: attrs>=22.2.0 in /opt/conda/lib/python3.12/site-packages (from jsonschema>=2.6->nbformat) (25.1.0)
Requirement already satisfied: jsonschema-specifications>=2023.03.6 in /opt/conda/lib/python3.12/site-packages (from jsonschema>=2.6->nbformat) (2024.10.1)
Requirement already satisfied: referencing>=0.28.4 in /opt/conda/lib/python3.12/site-packages (from jsonschema>=2.6->nbformat) (0.36.2)
Requirement already satisfied: rpds-py>=0.7.1 in /opt/conda/lib/python3.12/site-packages (from jsonschema>=2.6->nbformat) (0.22.3)
Requirement already satisfied: platformdirs>=2.5 in /opt/conda/lib/python3.12/site-packages (from jupyter-core!=5.0.*,>=4.12->nbformat) (4.3.6)
Requirement already satisfied: typing-extensions>=4.4.0 in /opt/conda/lib/python3.12/site-packages (from referencing>=0.28.4->jsonschema>=2.6->nbformat) (4.12.2)
import yfinance as yf
import pandas as pd
import requests
from bs4 import BeautifulSoup
import plotly.graph_objects as go
from plotly.subplots import make_subplots
In Python, you can ignore warnings using the warnings module. You can use the filterwarnings function to filter or ignore specific warning messages or categories.
import warnings
# Ignore all warnings
warnings.filterwarnings("ignore", category=FutureWarning)
Define Graphing Function¶
In this section, we define the function make_graph. You don't have to know how the function works, you should only care about the inputs. It takes a dataframe with stock data (dataframe must contain Date and Close columns), a dataframe with revenue data (dataframe must contain Date and Revenue columns), and the name of the stock.
def make_graph(stock_data, revenue_data, stock):
fig = make_subplots(rows=2, cols=1, shared_xaxes=True, subplot_titles=("Historical Share Price", "Historical Revenue"), vertical_spacing = .3)
stock_data_specific = stock_data[stock_data.Date <= '2021-06-14']
revenue_data_specific = revenue_data[revenue_data.Date <= '2021-04-30']
fig.add_trace(go.Scatter(x=pd.to_datetime(stock_data_specific.Date, infer_datetime_format=True), y=stock_data_specific.Close.astype("float"), name="Share Price"), row=1, col=1)
fig.add_trace(go.Scatter(x=pd.to_datetime(revenue_data_specific.Date, infer_datetime_format=True), y=revenue_data_specific.Revenue.astype("float"), name="Revenue"), row=2, col=1)
fig.update_xaxes(title_text="Date", row=1, col=1)
fig.update_xaxes(title_text="Date", row=2, col=1)
fig.update_yaxes(title_text="Price ($US)", row=1, col=1)
fig.update_yaxes(title_text="Revenue ($US Millions)", row=2, col=1)
fig.update_layout(showlegend=False,
height=900,
title=stock,
xaxis_rangeslider_visible=True)
fig.show()
Use the make_graph function that we’ve already defined. You’ll need to invoke it in questions 5 and 6 to display the graphs and create the dashboard.
Note: You don’t need to redefine the function for plotting graphs anywhere else in this notebook; just use the existing function.
Question 1: Use yfinance to Extract Stock Data¶
Using the Ticker function enter the ticker symbol of the stock we want to extract data on to create a ticker object. The stock is Tesla and its ticker symbol is TSLA.
import yfinance as yf
tesla_ticker = yf.Ticker("TSLA")
print(tesla_ticker)
yfinance.Ticker object <TSLA>
Using the ticker object and the function history extract stock information and save it in a dataframe named tesla_data. Set the period parameter to "max" so we get information for the maximum amount of time.
tesla_data = tesla_ticker.history(period="max")
print(tesla_data.head())
Open High Low Close Volume \
Date
2010-06-29 00:00:00-04:00 1.266667 1.666667 1.169333 1.592667 281494500
2010-06-30 00:00:00-04:00 1.719333 2.028000 1.553333 1.588667 257806500
2010-07-01 00:00:00-04:00 1.666667 1.728000 1.351333 1.464000 123282000
2010-07-02 00:00:00-04:00 1.533333 1.540000 1.247333 1.280000 77097000
2010-07-06 00:00:00-04:00 1.333333 1.333333 1.055333 1.074000 103003500
Dividends Stock Splits
Date
2010-06-29 00:00:00-04:00 0.0 0.0
2010-06-30 00:00:00-04:00 0.0 0.0
2010-07-01 00:00:00-04:00 0.0 0.0
2010-07-02 00:00:00-04:00 0.0 0.0
2010-07-06 00:00:00-04:00 0.0 0.0
Reset the index using the reset_index(inplace=True) function on the tesla_data DataFrame and display the first five rows of the tesla_data dataframe using the head function. Take a screenshot of the results and code from the beginning of Question 1 to the results below.
import pandas as pd
tesla_data = tesla_ticker.history(period="max")
tesla_data.reset_index(inplace=True)
print(tesla_data.head())
Date Open High Low Close \
0 2010-06-29 00:00:00-04:00 1.266667 1.666667 1.169333 1.592667
1 2010-06-30 00:00:00-04:00 1.719333 2.028000 1.553333 1.588667
2 2010-07-01 00:00:00-04:00 1.666667 1.728000 1.351333 1.464000
3 2010-07-02 00:00:00-04:00 1.533333 1.540000 1.247333 1.280000
4 2010-07-06 00:00:00-04:00 1.333333 1.333333 1.055333 1.074000
Volume Dividends Stock Splits
0 281494500 0.0 0.0
1 257806500 0.0 0.0
2 123282000 0.0 0.0
3 77097000 0.0 0.0
4 103003500 0.0 0.0
Question 2: Use Webscraping to Extract Tesla Revenue Data¶
Use the requests library to download the webpage https://cf-courses-data.s3.us.cloud-object-storage.appdomain.cloud/IBMDeveloperSkillsNetwork-PY0220EN-SkillsNetwork/labs/project/revenue.htm Save the text of the response as a variable named html_data.
import requests
url = "https://cf-courses-data.s3.us.cloud-object-storage.appdomain.cloud/IBMDeveloperSkillsNetwork-PY0220EN-SkillsNetwork/labs/project/revenue.htm"
response = requests.get(url)
html_data = response.text
print(html_data[:500])
<!DOCTYPE html>
<!--[if lt IE 7]> <html class="no-js lt-ie9 lt-ie8 lt-ie7"> <![endif]-->
<!--[if IE 7]> <html class="no-js lt-ie9 lt-ie8"> <![endif]-->
<!--[if IE 8]> <html class="no-js lt-ie9"> <![endif]-->
<!--[if gt IE 8]><!--> <html class="no-js"> <!--<![endif]-->
<head>
<meta charset="utf-8">
<meta http-equiv="X-UA-Compatible" content="IE=edge,chrome=1">
<link rel="canonical" href="https://www.macrotrends.net/stocks/charts/TSLA/tesla/revenue" />
Parse the html data using beautiful_soup using parser i.e html5lib or html.parser.
!pip install beautifulsoup4 html5lib
Requirement already satisfied: beautifulsoup4 in /opt/conda/lib/python3.12/site-packages (4.12.3) Requirement already satisfied: html5lib in /opt/conda/lib/python3.12/site-packages (1.1) Requirement already satisfied: soupsieve>1.2 in /opt/conda/lib/python3.12/site-packages (from beautifulsoup4) (2.5) Requirement already satisfied: six>=1.9 in /opt/conda/lib/python3.12/site-packages (from html5lib) (1.17.0) Requirement already satisfied: webencodings in /opt/conda/lib/python3.12/site-packages (from html5lib) (0.5.1)
import requests
from bs4 import BeautifulSoup
url = "https://cf-courses-data.s3.us.cloud-object-storage.appdomain.cloud/IBMDeveloperSkillsNetwork-PY0220EN-SkillsNetwork/labs/project/revenue.htm"
response = requests.get(url)
html_data = response.text
soup = BeautifulSoup(html_data, 'html.parser')
print(soup.prettify()[:500])
<!DOCTYPE html> <!--[if lt IE 7]> <html class="no-js lt-ie9 lt-ie8 lt-ie7"> <![endif]--> <!--[if IE 7]> <html class="no-js lt-ie9 lt-ie8"> <![endif]--> <!--[if IE 8]> <html class="no-js lt-ie9"> <![endif]--> <!--[if gt IE 8]><!--> <html class="no-js"> <!--<![endif]--> <head> <meta charset="utf-8"/> <meta content="IE=edge,chrome=1" http-equiv="X-UA-Compatible"/> <link href="https://www.macrotrends.net/stocks/charts/TSLA/tesla/revenue" rel="canonical"/> <title> Te
Using BeautifulSoup or the read_html function extract the table with Tesla Revenue and store it into a dataframe named tesla_revenue. The dataframe should have columns Date and Revenue.
Step-by-step instructions
Here are the step-by-step instructions:
1. Create an Empty DataFrame
2. Find the Relevant Table
3. Check for the Tesla Quarterly Revenue Table
4. Iterate Through Rows in the Table Body
5. Extract Data from Columns
6. Append Data to the DataFrame
Click here if you need help locating the table
Below is the code to isolate the table, you will now need to loop through the rows and columns like in the previous lab
soup.find_all("tbody")[1]
If you want to use the read_html function the table is located at index 1
We are focusing on quarterly revenue in the lab.
import requests
import pandas as pd
from bs4 import BeautifulSoup
url = "https://cf-courses-data.s3.us.cloud-object-storage.appdomain.cloud/IBMDeveloperSkillsNetwork-PY0220EN-SkillsNetwork/labs/project/revenue.htm"
response = requests.get(url)
html_data = response.text
soup = BeautifulSoup(html_data, 'html.parser')
tesla_revenue = pd.read_html(str(soup))[1]
tesla_revenue.columns = ['Date', 'Revenue']
tesla_revenue['Revenue'] = tesla_revenue['Revenue'].str.replace(',', '').str.replace('$', '')
print(tesla_revenue.head())
Date Revenue 0 2022-09-30 21454 1 2022-06-30 16934 2 2022-03-31 18756 3 2021-12-31 17719 4 2021-09-30 13757
Execute the following line to remove the comma and dollar sign from the Revenue column.
tesla_revenue["Revenue"] = tesla_revenue['Revenue'].str.replace(',|\$',"")
Execute the following lines to remove an null or empty strings in the Revenue column.
tesla_revenue.dropna(inplace=True)
tesla_revenue = tesla_revenue[tesla_revenue['Revenue'] != ""]
Display the last 5 row of the tesla_revenue dataframe using the tail function. Take a screenshot of the results.
import requests
import pandas as pd
from bs4 import BeautifulSoup
url = "https://cf-courses-data.s3.us.cloud-object-storage.appdomain.cloud/IBMDeveloperSkillsNetwork-PY0220EN-SkillsNetwork/labs/project/revenue.htm"
response = requests.get(url)
html_data = response.text
soup = BeautifulSoup(html_data, 'html.parser')
tesla_revenue = pd.read_html(str(soup))[1]
tesla_revenue.columns = ['Date', 'Revenue']
tesla_revenue['Revenue'] = tesla_revenue['Revenue'].str.replace(',', '').str.replace('$', '')
print(tesla_revenue.tail())
Date Revenue 49 2010-06-30 28 50 2010-03-31 21 51 2009-12-31 NaN 52 2009-09-30 46 53 2009-06-30 27
Question 3: Use yfinance to Extract Stock Data¶
Using the Ticker function enter the ticker symbol of the stock we want to extract data on to create a ticker object. The stock is GameStop and its ticker symbol is GME.
gamestop_ticker = yf.Ticker("GME")
print(gamestop_ticker)
yfinance.Ticker object <GME>
Using the ticker object and the function history extract stock information and save it in a dataframe named gme_data. Set the period parameter to "max" so we get information for the maximum amount of time.
gamestop_ticker = yf.Ticker("GME")
gme_data = gamestop_ticker.history(period="max")
print(gme_data.head())
Open High Low Close Volume \
Date
2002-02-13 00:00:00-05:00 1.620128 1.693350 1.603296 1.691667 76216000
2002-02-14 00:00:00-05:00 1.712707 1.716073 1.670626 1.683250 11021600
2002-02-15 00:00:00-05:00 1.683250 1.687458 1.658002 1.674834 8389600
2002-02-19 00:00:00-05:00 1.666418 1.666418 1.578047 1.607504 7410400
2002-02-20 00:00:00-05:00 1.615921 1.662210 1.603296 1.662210 6892800
Dividends Stock Splits
Date
2002-02-13 00:00:00-05:00 0.0 0.0
2002-02-14 00:00:00-05:00 0.0 0.0
2002-02-15 00:00:00-05:00 0.0 0.0
2002-02-19 00:00:00-05:00 0.0 0.0
2002-02-20 00:00:00-05:00 0.0 0.0
Reset the index using the reset_index(inplace=True) function on the gme_data DataFrame and display the first five rows of the gme_data dataframe using the head function. Take a screenshot of the results and code from the beginning of Question 3 to the results below.
gamestop_ticker = yf.Ticker("GME")
# Extract stock information and save it in a dataframe named gme_data
gme_data = gamestop_ticker.history(period="max")
# Reset the index of the gme_data dataframe
gme_data.reset_index(inplace=True)
# Display the first five rows of the gme_data dataframe
print(gme_data.head())
Date Open High Low Close Volume \ 0 2002-02-13 00:00:00-05:00 1.620129 1.693350 1.603296 1.691667 76216000 1 2002-02-14 00:00:00-05:00 1.712707 1.716073 1.670626 1.683250 11021600 2 2002-02-15 00:00:00-05:00 1.683250 1.687458 1.658002 1.674834 8389600 3 2002-02-19 00:00:00-05:00 1.666418 1.666418 1.578047 1.607504 7410400 4 2002-02-20 00:00:00-05:00 1.615920 1.662210 1.603296 1.662210 6892800 Dividends Stock Splits 0 0.0 0.0 1 0.0 0.0 2 0.0 0.0 3 0.0 0.0 4 0.0 0.0
Question 4: Use Webscraping to Extract GME Revenue Data¶
Use the requests library to download the webpage https://cf-courses-data.s3.us.cloud-object-storage.appdomain.cloud/IBMDeveloperSkillsNetwork-PY0220EN-SkillsNetwork/labs/project/stock.html. Save the text of the response as a variable named html_data_2.
import requests
url = "https://cf-courses-data.s3.us.cloud-object-storage.appdomain.cloud/IBMDeveloperSkillsNetwork-PY0220EN-SkillsNetwork/labs/project/stock.html"
response = requests.get(url)
html_data_2 = response.text
print(html_data_2[:500])
<!DOCTYPE html> <!-- saved from url=(0105)https://web.archive.org/web/20200814131437/https://www.macrotrends.net/stocks/charts/GME/gamestop/revenue --> <html class=" js flexbox canvas canvastext webgl no-touch geolocation postmessage websqldatabase indexeddb hashchange history draganddrop websockets rgba hsla multiplebgs backgroundsize borderimage borderradius boxshadow textshadow opacity cssanimations csscolumns cssgradients cssreflections csstransforms csstransforms3d csstransitions fontface g
Parse the html data using beautiful_soup using parser i.e html5lib or html.parser.
import requests
from bs4 import BeautifulSoup
url = "https://cf-courses-data.s3.us.cloud-object-storage.appdomain.cloud/IBMDeveloperSkillsNetwork-PY0220EN-SkillsNetwork/labs/project/stock.html"
response = requests.get(url)
html_data_2 = response.text
soup = BeautifulSoup(html_data_2, 'html.parser')
print(soup.prettify()[:500])
<!DOCTYPE html> <!-- saved from url=(0105)https://web.archive.org/web/20200814131437/https://www.macrotrends.net/stocks/charts/GME/gamestop/revenue --> <html class="js flexbox canvas canvastext webgl no-touch geolocation postmessage websqldatabase indexeddb hashchange history draganddrop websockets rgba hsla multiplebgs backgroundsize borderimage borderradius boxshadow textshadow opacity cssanimations csscolumns cssgradients cssreflections csstransforms csstransforms3d csstransitions fontface ge
Using BeautifulSoup or the read_html function extract the table with GameStop Revenue and store it into a dataframe named gme_revenue. The dataframe should have columns Date and Revenue. Make sure the comma and dollar sign is removed from the Revenue column.
Note: Use the method similar to what you did in question 2.
Click here if you need help locating the table
Below is the code to isolate the table, you will now need to loop through the rows and columns like in the previous lab
soup.find_all("tbody")[1]
If you want to use the read_html function the table is located at index 1
import pandas as pd
gme_revenue = pd.read_html(str(soup))[1]
gme_revenue.columns = ['Date', 'Revenue']
gme_revenue['Revenue'] = gme_revenue['Revenue'].str.replace(',', '').str.replace('$', '')
print(gme_revenue.head())
Date Revenue 0 2020-04-30 1021 1 2020-01-31 2194 2 2019-10-31 1439 3 2019-07-31 1286 4 2019-04-30 1548
Display the last five rows of the gme_revenue dataframe using the tail function. Take a screenshot of the results.
print(gme_revenue.tail())
Date Revenue 57 2006-01-31 1667 58 2005-10-31 534 59 2005-07-31 416 60 2005-04-30 475 61 2005-01-31 709
Question 5: Plot Tesla Stock Graph¶
Use the make_graph function to graph the Tesla Stock Data, also provide a title for the graph. Note the graph will only show data upto June 2021.
Hint
You just need to invoke the make_graph function with the required parameter to print the graphs.The structure to call the `make_graph` function is `make_graph(tesla_data, tesla_revenue, 'Tesla')`.
def make_graph(stock_data, revenue_data, stock):
fig = make_subplots(rows=2, cols=1, shared_xaxes=True, subplot_titles=("Historical Share Price", "Historical Revenue"), vertical_spacing = .3)
stock_data_specific = stock_data[stock_data.Date <= '2021-06-30']
revenue_data_specific = revenue_data[revenue_data.Date <= '2021-04-30']
fig.add_trace(go.Scatter(x=pd.to_datetime(stock_data_specific.Date, infer_datetime_format=True), y=stock_data_specific.Close.astype("float"), name="Share Price"), row=1, col=1)
fig.add_trace(go.Scatter(x=pd.to_datetime(revenue_data_specific.Date, infer_datetime_format=True), y=revenue_data_specific.Revenue.astype("float"), name="Revenue"), row=2, col=1)
fig.update_xaxes(title_text="Date", row=1, col=1)
fig.update_xaxes(title_text="Date", row=2, col=1)
fig.update_yaxes(title_text="Price ($US)", row=1, col=1)
fig.update_yaxes(title_text="Revenue ($US Millions)", row=2, col=1)
fig.update_layout(showlegend=False,
height=900,
title=stock,
xaxis_rangeslider_visible=True)
fig.show()
tesla_ticker = yf.Ticker("TSLA")
tesla_data = tesla_ticker.history(period="max")
tesla_data.reset_index(inplace=True)
tesla_data = tesla_data[tesla_data['Date'] <= '2021-06-30']
url = "https://cf-courses-data.s3.us.cloud-object-storage.appdomain.cloud/IBMDeveloperSkillsNetwork-PY0220EN-SkillsNetwork/labs/project/revenue.htm"
response = requests.get(url)
html_data = response.text
soup = BeautifulSoup(html_data, 'html.parser')
tesla_revenue = pd.read_html(str(soup))[1]
tesla_revenue.columns = ['Date', 'Revenue']
tesla_revenue['Revenue'] = tesla_revenue['Revenue'].str.replace(',', '').str.replace('$', '').astype(float)
tesla_revenue['Date'] = pd.to_datetime(tesla_revenue['Date'])
tesla_revenue = tesla_revenue[tesla_revenue['Date'] <= '2021-06-30']
make_graph(tesla_data, tesla_revenue, 'Tesla')
/tmp/ipykernel_301/1338607383.py:13: UserWarning: The argument 'infer_datetime_format' is deprecated and will be removed in a future version. A strict version of it is now the default, see https://pandas.pydata.org/pdeps/0004-consistent-to-datetime-parsing.html. You can safely remove this argument. /tmp/ipykernel_301/1338607383.py:14: UserWarning: The argument 'infer_datetime_format' is deprecated and will be removed in a future version. A strict version of it is now the default, see https://pandas.pydata.org/pdeps/0004-consistent-to-datetime-parsing.html. You can safely remove this argument.
Question 6: Plot GameStop Stock Graph¶
Use the make_graph function to graph the GameStop Stock Data, also provide a title for the graph. The structure to call the make_graph function is make_graph(gme_data, gme_revenue, 'GameStop'). Note the graph will only show data upto June 2021.
Hint
You just need to invoke the make_graph function with the required parameter to print the graphs.The structure to call the `make_graph` function is `make_graph(gme_data, gme_revenue, 'GameStop')`
def make_graph(stock_data, revenue_data, stock):
fig = make_subplots(rows=2, cols=1, shared_xaxes=True, subplot_titles=("Historical Share Price", "Historical Revenue"), vertical_spacing = .3)
stock_data_specific = stock_data[stock_data.Date <= '2021-06-30']
revenue_data_specific = revenue_data[revenue_data.Date <= '2021-04-30']
fig.add_trace(go.Scatter(x=pd.to_datetime(stock_data_specific.Date, infer_datetime_format=True), y=stock_data_specific.Close.astype("float"), name="Share Price"), row=1, col=1)
fig.add_trace(go.Scatter(x=pd.to_datetime(revenue_data_specific.Date, infer_datetime_format=True), y=revenue_data_specific.Revenue.astype("float"), name="Revenue"), row=2, col=1)
fig.update_xaxes(title_text="Date", row=1, col=1)
fig.update_xaxes(title_text="Date", row=2, col=1)
fig.update_yaxes(title_text="Price ($US)", row=1, col=1)
fig.update_yaxes(title_text="Revenue ($US Millions)", row=2, col=1)
fig.update_layout(showlegend=False,
height=900,
title=stock,
xaxis_rangeslider_visible=True)
fig.show()
gamestop_ticker = yf.Ticker("GME")
gme_data = gamestop_ticker.history(period="max")
gme_data.reset_index(inplace=True)
gme_data = gme_data[gme_data['Date'] <= '2021-06-30']
url = "https://cf-courses-data.s3.us.cloud-object-storage.appdomain.cloud/IBMDeveloperSkillsNetwork-PY0220EN-SkillsNetwork/labs/project/stock.html"
response = requests.get(url)
html_data_2 = response.text
soup = BeautifulSoup(html_data_2, 'html.parser')
gme_revenue = pd.read_html(str(soup))[1]
gme_revenue.columns = ['Date', 'Revenue']
gme_revenue['Revenue'] = gme_revenue['Revenue'].str.replace(',', '').str.replace('$', '').astype(float)
gme_revenue['Date'] = pd.to_datetime(gme_revenue['Date'])
gme_revenue = gme_revenue[gme_revenue['Date'] <= '2021-06-30']
make_graph(gme_data, gme_revenue, 'GameStop')
/tmp/ipykernel_301/1029891731.py:13: UserWarning: The argument 'infer_datetime_format' is deprecated and will be removed in a future version. A strict version of it is now the default, see https://pandas.pydata.org/pdeps/0004-consistent-to-datetime-parsing.html. You can safely remove this argument. /tmp/ipykernel_301/1029891731.py:14: UserWarning: The argument 'infer_datetime_format' is deprecated and will be removed in a future version. A strict version of it is now the default, see https://pandas.pydata.org/pdeps/0004-consistent-to-datetime-parsing.html. You can safely remove this argument.
About the Authors:
Joseph Santarcangelo has a PhD in Electrical Engineering, his research focused on using machine learning, signal processing, and computer vision to determine how videos impact human cognition. Joseph has been working for IBM since he completed his PhD.
Azim Hirjani
Change Log¶
| Date (YYYY-MM-DD) | Version | Changed By | Change Description |
|---|---|---|---|
| 2022-02-28 | 1.2 | Lakshmi Holla | Changed the URL of GameStop |
| 2020-11-10 | 1.1 | Malika Singla | Deleted the Optional part |
| 2020-08-27 | 1.0 | Malika Singla | Added lab to GitLab |
© IBM Corporation 2020. All rights reserved.